agent-browser-clawdbot-roseHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Install via ClawdBot CLI:
clawdbot install roseknife520/agent-browser-clawdbot-roseGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/vercel-labs/agent-browserAudited Apr 18, 2026 · audit v1.0
Generated May 5, 2026
Use agent-browser to navigate to multiple web pages, extract structured data (e.g., product listings, pricing), and save the results. The tool's accessibility tree snapshots and ref-based selection ensure deterministic extraction from SPAs.
Run simultaneous browser sessions with different user roles (admin, user) to test application behavior. Save and load auth states to skip repeated logins, and use network mocking to simulate API responses.
Automate complex form workflows by filling fields, selecting options, and submitting. Use snapshot to verify changes and wait commands to ensure page stability before interaction.
Scrape data behind login walls by saving cookies/localStorage after authentication and reusing them across sessions. Use isolated sessions to manage multiple accounts simultaneously.
Take snapshots of key pages after actions (clicks, fills) and compare element states like visibility or text content. Use compact snapshot options to focus on interactive elements and speed up tests.
Integrate agent-browser into a SaaS platform to offer headless browser automation for customers. Charge per session or per API call, leveraging isolated sessions for multi-tenancy.
Provide custom web scraping solutions for businesses needing structured data from dynamic websites. Use agent-browser's deterministic element selection to ensure high accuracy and reliability.
Offer agent-browser as a plugin or add-on to existing CI/CD pipelines and testing frameworks. Sell licenses for enterprise use, with premium support for complex session management and state persistence.
💬 Integration Tip
Use the AGENT_BROWSER_SESSION environment variable to set the session name when running commands, and always include -i --json flags on snapshots for consistent parsing.
Scored Jun 27, 2026
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Uses a headless browser to navigate web pages, interact with elements, and extract clean, readable text content from URLs.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
通过已登录的Edge或Chrome浏览器,利用Chrome DevTools Protocol执行JS渲染页面的导航、点击、截图及数据提取等自动化操作。
Send and receive SMS/RCS via Google Messages web interface (messages.google.com). Use when asked to "send a text", "check texts", "SMS", "text message", "Google Messages", or forward incoming texts to other channels.
High-performance browser automation for heavy scraping, multi-tab management, and precise DOM extraction. Use this when you need speed, reliability, or advanced state management (cookies/local storage) beyond standard web fetching.